Chapter
The Future of Self-Driving Cars: Learning vs. No-Learning Approaches
1:06:46 - 1:09:58 (03:12)
The possibility of achieving level five self-driving vehicles without any machine learning is discussed, with questions raised about whether or not it is a feasible approach. The motivations behind other companies' promises to deliver L5 vehicles within the next few years are examined in comparison to Google's Waymo.
Clips
Andre Carpathie, the Director of AI and Autopilot Vision at Tesla, believes that machine learning is the way forward for self-driving cars - a method that involves turning everything into a learning problem and collecting a huge amount of data.
1:06:46 - 1:07:50 (01:04)
Summary
Andre Carpathie, the Director of AI and Autopilot Vision at Tesla, believes that machine learning is the way forward for self-driving cars - a method that involves turning everything into a learning problem and collecting a huge amount of data. However, not every problem can be solved with machine learning in the short term, and building L5 vehicles today is unlikely to involve learning, making LiDAR a necessary crutch for the time being.
ChapterThe Future of Self-Driving Cars: Learning vs. No-Learning Approaches
EpisodeGeorge Hotz: Comma.ai, OpenPilot, and Autonomous Vehicles
PodcastLex Fridman Podcast
The discussion revolves around the advancements made by Waymo in developing level 4 autonomous vehicles and the timeline declared by other companies including Ford in achieving level 5 self-driving cars in the coming years.
1:07:50 - 1:09:58 (02:07)
Summary
The discussion revolves around the advancements made by Waymo in developing level 4 autonomous vehicles and the timeline declared by other companies including Ford in achieving level 5 self-driving cars in the coming years.